Qwen3.5-2B benchmark on an M4 · 24 GB

{
  "runId": "run_97f00217-f2a3-4bbc-b459-86d1f02268f5",
  "bundleId": "llamacpp-qwen3.5-2b-q5_k_s.gguf-15df49",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.21",
    "gitSha": "50c24e0"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b9260",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Qwen3.5-2B",
    "format": "gguf",
    "quant": "q5_k_s",
    "architecture": "qwen35",
    "source": "unsloth/Qwen3.5-2B-GGUF:Qwen3.5-2B-Q5_K_S.gguf",
    "fileSizeBytes": 1384546560,
    "lab": {
      "name": "Qwen",
      "slug": "qwen"
    },
    "quantizedBy": {
      "name": "Unsloth",
      "slug": "unsloth"
    }
  },
  "device": {
    "cpu": "Apple M4",
    "cpuCores": 10,
    "gpu": "Apple M4",
    "gpuCores": 10,
    "gpuCount": 1,
    "ramGb": 24,
    "osName": "macOS",
    "osVersion": "26.5"
  },
  "decodeTpsMean": 52.4,
  "prefillTpsMean": 860,
  "ttftP50Ms": 4690.48,
  "idleTpsMean": 0,
  "peakRssMb": 865.3,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.7995103655133928,
  "bundleSha256": "35d394b87612116bbdd40608738561fb6ae68bc6c1ba6a200d943758c5d0ceb6",
  "createdAt": "2026-05-24T07:39:35.520Z"
}